Repository navigation
Package Native, Vulkan, and GGML as an executorch-native wheel (#24069) - #24069
JakeStevens wants to merge 2 commits into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24069
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 Unclassified FailuresAs of commit 3dbe48c with merge base 141f543 ( UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D126459370. |
This PR needs a
|
executorch-native wheelexecutorch-native wheel (#24069)
…orch#24069) Summary: Add a Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime. The separate package coexists with `executorch`; Python execution bindings remain out of scope. Authored with assistance from Codex. Differential Revision: D126459370
c69e882 to
88d093a
Compare
…orch#24069) Summary: Add a Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime. The separate package coexists with `executorch`; Python execution bindings remain out of scope. Authored with assistance from Codex. Differential Revision: D126459370
88d093a to
847d29b
Compare
Summary: Extend the shared `FuseBatchNormWithConvPass` to fold frozen evaluation BatchNorm during Native AOT export, using a thin `ExportedProgram` adapter in Native's default pass pipeline. Preserve existing `GraphModule` callers and grouped/transposed convolution support. Functionalize all methods before collecting mutable buffers. This protects running statistics updated by another `.ptn` method while allowing folding through `ReLU(inplace=True)`. Authored with assistance from Codex. Differential Revision: D126696057
…orch#24069) Summary: Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with `executorch`. Keep the standalone wheel recipe in `backends/native/python` and its Python wrappers alongside the runtime in `backends/native/pybindings`. CMake installs those sources into `executorch_native`; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff. Authored with assistance from Codex. Differential Revision: D126459370
847d29b to
3dbe48c
Compare
…orch#24069) Summary: Pull Request resolved: pytorch#24069 Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with `executorch`. Keep the standalone wheel recipe in `backends/native/python` and its Python wrappers alongside the runtime in `backends/native/pybindings`. CMake installs those sources into `executorch_native`; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff. Authored with assistance from Codex. Differential Revision: D126459370
Summary:
Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with
executorch.Keep the standalone wheel recipe in
backends/native/pythonand its Python wrappers alongside the runtime inbackends/native/pybindings. CMake installs those sources intoexecutorch_native; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff.Authored with assistance from Codex.
Differential Revision: D126459370